A Benchmark and Simulator for UAV Tracking
- Matthias Mueller, Neil G. Smith, Bernard Ghanem
- Computer ScienceEuropean Conference on Computer Vision
- 8 October 2016
A new aerial video dataset and benchmark for low altitude UAV target tracking, as well as, a photo-realistic UAV simulator that can be coupled with tracking methods to easily extend existing real-world datasets.
ActivityNet: A large-scale video benchmark for human activity understanding
- Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, Juan Carlos Niebles
- Computer ScienceComputer Vision and Pattern Recognition
- 7 June 2015
This paper introduces ActivityNet, a new large-scale video benchmark for human activity understanding that aims at covering a wide range of complex human activities that are of interest to people in their daily living.
The Visual Object Tracking VOT2016 Challenge Results
- M. Kristan, A. Leonardis, Zhizhen Chi
- Computer ScienceECCV Workshops
- 8 October 2016
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
- Matthias Müller, Adel Bibi, Silvio Giancola, Salman Al-Subaihi, Bernard Ghanem
- Computer ScienceEuropean Conference on Computer Vision
- 28 March 2018
This work presents TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild, which covers a wide selection of object classes in broad and diverse context and provides an extensive benchmark on TrackingNet by evaluating more than 20 trackers.
Robust visual tracking via multi-task sparse learning
- Tianzhu Zhang, Bernard Ghanem, Si Liu, N. Ahuja
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 16 June 2012
Experimental results show that MTT methods consistently outperform state-of-the-art trackers and mining the interdependencies between particles improves tracking performance and overall computational complexity.
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
- Jian Zhang, Bernard Ghanem
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 24 June 2017
This paper proposes a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $$ norm CS reconstruction model and develops an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms.
Context-Aware Correlation Filter Tracking
- Matthias Mueller, Neil G. Smith, Bernard Ghanem
- Computer ScienceComputer Vision and Pattern Recognition
- 11 April 2017
This paper reformulate the original optimization problem and provides a closed form solution for single and multi-dimensional features in the primal and dual domain and significantly improves the performance of many CF trackers with only a modest impact on frame rate.
DeepGCNs: Can GCNs Go As Deep As CNNs?
- G. Li, Matthias Müller, Ali K. Thabet, Bernard Ghanem
- Computer ScienceIEEE International Conference on Computer Vision
- 7 April 2019
This work presents new ways to successfully train very deep GCNs by borrowing concepts from CNNs, specifically residual/dense connections and dilated convolutions, and adapting them to GCN architectures, and building a very deep 56-layer GCN.
G-TAD: Sub-Graph Localization for Temporal Action Detection
- Mengmeng Xu, Chen Zhao, D. Rojas, Ali K. Thabet, Bernard Ghanem
- Computer ScienceComputer Vision and Pattern Recognition
- 26 November 2019
This work proposes a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem.
The Visual Object Tracking VOT2015 Challenge Results
- M. Kristan, Jiri Matas, Zhibin Hong
- Computer Science
- 2018
The Visual Object Tracking challenge 2015, VOT 2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and presents a new VOT2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute.
...
...